Open AccessPosted Content
A fast accurate fine-grain object detection model based on YOLOv4 deep neural network.
Reads0
Chats0
TLDR
In this article, the authors presented a real-time fine-grain object detection framework that addresses several obstacles in plant disease detection that hinder the performance of traditional methods, such as, dense distribution, irregular morphology, multi-scale object classes, textural similarity, etc.Abstract:
Early identification and prevention of various plant diseases in commercial farms and orchards is a key feature of precision agriculture technology. This paper presents a high-performance real-time fine-grain object detection framework that addresses several obstacles in plant disease detection that hinder the performance of traditional methods, such as, dense distribution, irregular morphology, multi-scale object classes, textural similarity, etc. The proposed model is built on an improved version of the You Only Look Once (YOLOv4) algorithm. The modified network architecture maximizes both detection accuracy and speed by including the DenseNet in the back-bone to optimize feature transfer and reuse, two new residual blocks in the backbone and neck enhance feature extraction and reduce computing cost; the Spatial Pyramid Pooling (SPP) enhances receptive field, and a modified Path Aggregation Network (PANet) preserves fine-grain localized information and improve feature fusion. Additionally, the use of the Hard-Swish function as the primary activation improved the model's accuracy due to better nonlinear feature extraction. The proposed model is tested in detecting four different diseases in tomato plants under various challenging environments. The model outperforms the existing state-of-the-art detection models in detection accuracy and speed. At a detection rate of 70.19 FPS, the proposed model obtained a precision value of $90.33 \%$, F1-score of $93.64 \%$, and a mean average precision ($mAP$) value of $96.29 \%$. Current work provides an effective and efficient method for detecting different plant diseases in complex scenarios that can be extended to different fruit and crop detection, generic disease detection, and various automated agricultural detection processes.read more
Citations
More filters
Journal ArticleDOI
Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv4
Ajit K. Roy,Jayabrata Bhaduri +1 more
TL;DR: In this article , the authors proposed a real-time object detection framework Dense-YOLOv4 based on an improved version of the YOLO-v4 algorithm by including DenseNet in the backbone to optimize feature transfer and reuse.
Posted ContentDOI
An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces
TL;DR: An efficient multi-scale convolutional neural network (MS-CNN) which can extract the distinguishable features of several non-overlapping canonical frequency bands of EEG signals from multiple scales for MI-BCI classification is proposed.
Journal ArticleDOI
Swin-Transformer-Enabled YOLOv5 with Attention Mechanism for Small Object Detection on Satellite Images
Hang Gong,Ting-Ming Mu,Qiuxia Li,Hai Tao Dai,Chunlai Li,Zhiping He,Wenjing Wang,Fenglin Han,Abudusalamu Tuniyazi,Haoyang Li,Xuechan Lang,Zhiyuan Li,Bin Wang +12 more
TL;DR: Wang et al. as discussed by the authors modified the general one-stage detector YOLOv5 to adapt the satellite images to resolve the intrinsic differences in the scale and orientation of objects generated by the bird's-eye perspective of satellite photographs.
Journal ArticleDOI
Hyper-sausage coverage function neuron model and learning algorithm for image classification
TL;DR: Wang et al. as mentioned in this paper proposed a hyper-sausage coverage function (HSCF) neuron model possessing a high flexible plasticity, and a novel cross-entropy and volume-coverage (CE_VC) loss is defined, which compresses the volume of the HSCF to the hilt, and helps alleviate confusion among different classes.
Journal ArticleDOI
Deep Learning Based Detector YOLOv5 for Identifying Insect Pests
TL;DR: In this paper , an object recognition system based on the YOLO object detection architecture was proposed to detect insect pests from digital images/videos to reduce farmers' reliance on pesticides.
References
More filters
Posted Content
YOLOv3: An Incremental Improvement.
Joseph Redmon,Ali Farhadi +1 more
TL;DR: The authors present some updates to YOLO!
Posted Content
YOLOv4: Optimal Speed and Accuracy of Object Detection
TL;DR: This work uses new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, C mBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.
Posted Content
SGDR: Stochastic Gradient Descent with Warm Restarts
Ilya Loshchilov,Frank Hutter +1 more
TL;DR: In this paper, a simple warm restart technique for stochastic gradient descent was proposed to improve its anytime performance when training deep neural networks, which achieved state-of-the-art results on both the CIFAR-10 and CifAR-100 datasets.
Posted Content
Searching for Activation Functions
TL;DR: In this paper, a combination of exhaustive and reinforcement learning-based search is proposed to discover multiple novel activation functions, including Swish, which is the most successful and widely used activation function in deep networks.
Proceedings Article
DropBlock: A regularization method for convolutional networks
TL;DR: DropBlock as discussed by the authors introduces DropBlock, a form of structured dropout, where units in a contiguous region of a feature map are dropped together and applies DropbBlock in skip connections in addition to the convolution layers.